Motion Compensation Technique Research Articles

Respiration-Induced Organ Motion Compensation: A Review.

Motion of organs in the abdominal and thoracic cavity caused by respiration is a major issue that affects a wide range of clinical diagnoses or treatment outcomes, including radiotherapy, high-intensity focused ultrasound ablation, and many generalized percutaneous needle interventions. These motions pose significant challenges in accurately reaching the target even for the experienced clinician. This review was conducted through comprehensive search on IEEE Explore, Google Scholar, and PubMed. Diverse methods have been proposed to compensate for this motion effect to enable effective surgical operations. This review paper aims to examine the current respiratory motion compensation techniques used across the clinical procedures of radiotherapy, high-intensity focused ultrasound, and percutaneous needle procedures. The complexity of respiratory-induced organ motion and diversity of areas for which compensation can be applied allows for a variety of methodsto be implemented. This review aims to serve as inspiration for the future development of new systems to achieve clinical relevance.

Single detector compound axis system employs a two-axis mirror to achieve target acquisition.

Airborne electro-optical countermeasure systems necessitate designs that are both lightweight and miniaturized. This study examines a single-detector composite-axis system that integrates a large-stroke, large-aperture two-axis mirror for coarse tracking tasks and a piezoelectric fast-steering mirror for fine tracking adjustments. Addressing the system's initial pointing and spiral scanning challenges, the study derives dynamic target-pointing equations using coordinate transformation and optical geometry. Neural network fitting is utilized to analyze the coupling between the mechanical travel angle of the two-axis mirror and the optical angle changes. Scanning detection and image motion compensation techniques enhance the system's field of view. The paper also introduces the application of differential evolution algorithms for target positioning without distance information. Ground-to-air experiments substantiate the effectiveness of the proposed methods.

Phantoms for Quantitative Body MRI: a review and discussion of the phantom value.

In this paper, we review the value of phantoms for body MRI in the context of their uses for quantitative MRI methods research, clinical trials, and clinical imaging. Certain uses of phantoms are common throughout the body MRI community, including measuring bias, assessing reproducibility, and training. In addition to these uses, phantoms in body MRI methods research are used for novel methods development and the design of motion compensation and mitigation techniques. For clinical trials, phantoms are an essential part of quality management strategies, facilitating the conduct of ethically sound, reliable, and regulatorily compliant clinical research of both novel MRI methods and therapeutic agents. In the clinic, phantoms are used for development of protocols, mitigation of cost, quality control, and radiotherapy. We briefly review phantoms developed for quantitative body MRI, and finally, we review open questions regarding the most effective use of a phantom for body MRI.

Navigator-based motion compensation for liver BOLD measurement with five-echo SAGE EPI and breath-hold task.

The purpose of this work is to apply multi-echo spin- and gradient-echo (SAGE) echo-planar imaging (EPI) combined with a navigator-based (NAV) prospective motion compensation method for a quantitative liver blood oxygen level dependent (BOLD) measurement with a breath-hold (BH) task. A five-echo SAGE sequence was developed to quantitatively measure T2 and T2* to depict function with sufficient signal-to-noise ratio, spatial resolution and sensitivity to BOLD changes induced by the BH task. To account for respiratory motion, a navigator was employed in the form of a single gradient-echo projection readout, located at the diaphragm along the inferior-superior direction. Prior to each transverse imaging slice of the spin-echo EPI-based readouts, navigator acquisition and fat suppression were incorporated. Motion data was obtained from the navigator and transmitted back to the sequence, allowing real-time adjustments to slice positioning. Six healthy volunteers and three patients with liver carcinoma were included in this study. Quantitative T2 and T2* were calculated at each time point of the BH task. Parameters of t value from first-level analysis using a general linear model and hepatovascular reactivity (HVR) of Echo1, T2 and T2* were calculated. The motion caused by respiratory activity was successfully compensated using the navigator signal. The average changes of T2 and T2* during breath-hold were about 1% and 0.7%, respectively. With the help of NAV prospective motion compensation whole liver t values could be obtained without motion artifacts. The quantified liver T2 (34.7 ± 0.7 ms) and T2* (29 ± 1.2 ms) values agreed with values from literature. In healthy volunteers, the distribution of statistical t value and HVR was homogeneous throughout the whole liver. In patients with liver carcinoma, the distribution of t value and HVR was inhomogeneous due to metastases or therapy. This study demonstrates the feasibility of using a NAV prospective motion compensation technique in conjunction with five-echo SAGE EPI for the quantitative measurement of liver BOLD with a BH task.

High-resolution Diffusion-weighted Imaging to Detect Changes in Tumor Size and ADC, and Predict Adverse Biopsy Histology during Prostate Cancer Active Surveillance.

Majority of men with low-risk prostate cancer can be managed with active surveillance (AS). This study evaluates a high-resolution diffusion-weighted imaging (HR-DWI) technique to predict adverse biopsy histology (AH), defined as Gleason score ≥7 on any biopsy or ≥3 increase in number of positive biopsy cores on systematic biopsies. We test the hypothesis that high-grade disease and progressing disease undergo subtle changes during even short intervals that can be detected by HR-DWI. In a prospective clinical trial, serial multiparametric MRIs, incorporating HR-DWI and standard DWI (S-DWI) were performed approximately 12 months apart prior to prostate biopsy (n = 59). HR-DWI, which uses reduced field-of-view and motion compensation techniques, was compared with S-DWI. HR-DWI had a 3-fold improvement in spacial resolution compared with S-DWI as confirmed using imaging phantoms. For detecting AH, multiparametric MRI using HR-DWI had a sensitivity of 75% and specificity of 83.9%, and MRI using S-DWI had a sensitivity of 71.4% and specificity of 54.8%. The AUC for HR-DWI was significantly higher (0.794 vs. 0.631, P = 0.014). Secondary analyses of univariable predictors of AH showed tumor size increase [OR 16.8; 95% confidence interval (CI): 4.06-69.48; P < 0.001] and apparent diffusion coefficient (ADC) decrease (OR 5.06; 95% CI: 1.39-18.38; P = 0.014) on HR-DWI were significant predictors of AH. HR-DWI outperforms S-DWI in predicting AH. Patient with AH have tumors that change in size and ADC that could be detected using HR-DWI. Future studies with longer follow-up should assess HR-DWI for predicting disease progression during AS. We report on a prospective clinical trial using a MRI that has three times the resolution of standard MRI. During AS for prostate cancer, two high-resolution MRIs performed approximately a year apart can detect tumor changes that predict the presence of aggressive cancers that should be considered for curative therapy such as prostatectomy or radiation.

Smart-sight: Video-based waste characterization for RDF-3 production

A material recovery facility (MRF) can transform municipal solid waste (MSW) into a valued commodity called refuse-derived fuel (RDF) as a promising solution to waste-to-energy conversion. The quality of the produced RDF significantly relies on the composition of in-feed waste and waste characterization method applied for auditing purposes, a process that is both time-consuming and fraught with potential hazards. This study focuses to enhance the workflow of the waste characterization process at an MRF. A solution named Smart Sight is proposed to detect and classify waste based on videos recorded after processing MSW through a mechanical sorting line consisting of bag breakers and trommel screens. A comprehensive dataset is created encompassing thirteen mixed waste classes from single and multi-family streams. The dataset is preprocessed with motion compensation techniques and frame differencing methods to extract and refine valuable frames. A one-stage YOLO detector model is then trained over the dataset. The experimental results show that the proposed method works efficiently at detecting and classifying waste objects in indoor MRF environments. Accuracy, precision, recall, and F1 score related to the proposed solution are found to be 0.70, 0.762, 0.69 and 0.72, respectively, with a mAP@0.5 of 0.716. The proposed approach is validated using data collected from local MRF by comparing the estimated waste composition values of the proposed solution with laboratory results obtained through current standardized industrial practices. Comparison reveals that waste characterization estimation obtained is consistent with the laboratory results, inferring that Smart-Sight is a viable tool for estimating waste composition.

Contactless control of suspended loads for offshore installations: Proof of concept using magnetic interaction

Current offshore wind turbine installation and positioning methods require mechanical equipment attached on the lifted components and human intervention. The present paper studies the development of a contactless motion compensation technique by investigating a magnetically controlled pendulum. The technique involves the interaction of a magnetic pendulum with an electromagnetic actuator. Two control modes are considered: the imposition of a desired motion to the mass and the motion attenuation of a prescribed pivot excitation. The numerical model is validated and calibrated against experiments and demonstrates excellent predictive capabilities. The control exerted is effective for a broad range of excitation frequencies and amplitudes. Important parameters associated with the performance of the technique such as the separation distance of the magnets and the saturation of the controller are identified. The controllability regions for effective control depending on the characteristics of the excitation are derived. The force amplitude of the contactless actuator is comparable to currently-used active tugger line control systems, but with the additional advantage of both attractive and repulsive forces. The findings of this paper illuminate the path for the further development of a non-contact control technique which has the potential to increase the efficiency of offshore wind installations.

DPI-MoCo: Deep Prior Image Constrained Motion Compensation Reconstruction for 4D CBCT.

4D cone-beam computed tomography (CBCT) plays a critical role in adaptive radiation therapy for lung cancer. However, extremely sparse sampling projection data will cause severe streak artifacts in 4D CBCT images. Existing deep learning (DL) methods heavily rely on large labeled training datasets which are difficult to obtain in practical scenarios. Restricted by this dilemma, DL models often struggle with simultaneously retaining dynamic motions, removing streak degradations, and recovering fine details. To address the above challenging problem, we introduce a Deep Prior Image Constrained Motion Compensation framework (DPI-MoCo) that decouples the 4D CBCT reconstruction into two sub-tasks including coarse image restoration and structural detail fine-tuning. In the first stage, the proposed DPI-MoCo combines the prior image guidance, generative adversarial network, and contrastive learning to globally suppress the artifacts while maintaining the respiratory movements. After that, to further enhance the local anatomical structures, the motion estimation and compensation technique is adopted. Notably, our framework is performed without the need for paired datasets, ensuring practicality in clinical cases. In the Monte Carlo simulation dataset, the DPI-MoCo achieves competitive quantitative performance compared to the state-of-the-art (SOTA) methods. Furthermore, we test DPI-MoCo in clinical lung cancer datasets, and experiments validate that DPI-MoCo not only restores small anatomical structures and lesions but also preserves motion information.

Impact of respiratory motion on 18 F-FDG PET radiomics stability: Clinical evaluation with a digital PET scanner.

18 F-FDG PET quantitative features are susceptible to respiratory motion. However, studies using clinical patient data to explore the impact of respiratory motion on 18 F-FDG PET radiomic features are limited. In this study, we investigated the impact of respiratory motion on radiomics stability with clinical 18 F-FDG PET images using a data-driven gating (DDG) algorithm on the digital PET scanner. A total of 101 patients who underwent oncological 18 F-FDG PET scans were retrospectively included. A DDG algorithm combined with a motion compensation technique was used to extract the PET images with respiratory motion correction. 18 F-FDG-avid lesions from the thorax to the upper abdomen were analyzed on the non-DDG and DDG PET images. The lesions were segmented with a 40% threshold of the maximum standardized uptake. A total of 725 radiomic features were computed from the segmented lesions, including first-order, shape, texture, and wavelet features. The intraclass correlation coefficient (ICC) and coefficient of variation (COV) were calculated to evaluate feature stability. An ICC above 0.9 and a COV below 5% were considered high stability. In total, 168 lesions with and without respiratory motion correction were analyzed. Our results indicated that most 18 F-FDG PET radiomic features are sensitive to respiratory motion. Overall, only 27 out of 725 (3.72%) radiomic features were identified as highly stable, including one from the first-order features (entropy), one from the shape features (sphericity), four from the gray-level co-occurrence matrix features (normalized and unnormalized inverse difference moment, joint entropy, and sum entropy), one from the gray-level run-length matrix features (run entropy), and 20 from the wavelet filter-based features. Respiratory motion has a significant impact on 18 F-FDG PET radiomics stability. The highly stable features identified in our study may serve as potential candidates for further applications, such as machine learning modeling.

Computer Network Redundancy Reduction Using Video Compression

Due to the strong correlation between symmetric frames, video signals have a high degree of temporal redundancy. Motion estimation techniques are computationally expensive and time-consuming processes used in symmetric video compression to reduce temporal redundancy. The block-matching technique is, on the other hand, the most popular and efficient of the different motion estimation and compensation techniques. Motion compensation based on the block-matching technique generally uses the minimization of either the mean square error (MSE) or mean absolute difference (MAD) in order to find the appropriate motion vector. This paper proposes to remove the highly temporally redundant information contained in each block of the video signal using the removing temporal redundancy (RTR) technique in order to improve the data rate and efficiency of the video signal. A comparison between the PSNR values of this technique and those of the JPEG video compression standard is made. As a result of its moderate memory and computation requirements, the algorithm was found to be suitable for mobile networks and embedded devices. Based on a detailed set of testing scenarios and the obtained results, it is evident that the RTR compression technique allowed a compression ratio of 22.71 and 95% loss in bit rate reduction while maintaining sufficient intact signal quality with minimized information loss.

Assessment of Atmospheric and Oceanographic Measurements from an Autonomous Surface Vehicle

Abstract The present work details the measurement capabilities of Wave Glider autonomous surface vehicles (ASVs) for research-grade meteorology, wave, and current data. Methodologies for motion compensation are described and tested, including a correction technique to account for Doppler shifting of the wave signal. Wave Glider measurements are evaluated against observations obtained from World Meteorological Organization (WMO)-compliant moored buoy assets located off the coast of Southern California. The validation spans a range of field conditions and includes multiple deployments to assess the quality of vehicle-based observations. Results indicate that Wave Gliders can accurately measure wave spectral information, bulk wave parameters, water velocities, bulk winds, and other atmospheric variables with the application of appropriate motion compensation techniques. Measurement errors were found to be comparable to those from reference moored buoys and within WMO operational requirements. The findings of this study represent a step toward enabling the use of ASV-based data for the calibration and validation of remote observations and assimilation into forecast models.

Motion Estimation and Improved SAR Imaging for Agile Platforms Using Omnidirectional Radar and INS Sensor Fusion

Accurate motion estimation is a challenging problem for agile radar platforms, even when state-of-the-art inertial navigation sensors (INSs) are used. However, it is an important problem to solve as it can have a large impact on the performance of radar modes, such as synthetic aperture radar (SAR). This study addresses the motion estimation problem of agile radar platforms from the perspective of an omnidirectional radar array. In this study, we perform an analysis on the applicability of an omnidirectional radar array to explicitly estimate the motion of an agile SAR platform and improve imaging quality. Building on existing 1-D SAR motion compensation techniques, we develop a method to estimate the 3-D motion of the radar platform utilizing its height and velocity vector. Using a prototype radar developed at the Netherlands Organisation for Applied Scientific Research, we experimentally verify that using the proposed velocity estimation method alone, we achieve comparable positioning performance to that of a state-of-the-art INS, making it possible to perform INS-free SAR imaging by using arbitrary flight paths. We also show that fusing the radar positioning estimates obtained from the proposed methods with the INS output yields an additional increase in SAR imaging performance, improving the resolvability and detectability of weak targets.

Video Chatting Platform with Video Enhancing Feature Using Super Resolution

Abstract: This paper describes the process of creating a Multi-User Video Chatting Platform with Agora Video SDK and a Django Backend. The Video Super Resolution technique is being used to improve the quality of video calls. VSR is the process of reconstructing high-resolution videos from low-resolution ones. We employ the Dynamic Up sampling Filters Without Explicit Motion Compensation technique for VSR. We reconstruct an HR image directly from the input image using dynamic Up sampling filters, and the fine details are added using the computed residual.

Reducing PTV margins for prostate SBRT with motion compensation and gating techniques.

The purpose of this study is to investigate the dosimetric accuracy of prostate SBRT when motion is considered. To account for target movement, motion compensation and gating techniques were investigated with PTV margins reduced to 2mm. To allow for dosimetric measurements a Delta4 phantom, Gafchromic film, and Hexamotion motion platform were utilized. Four motion files were utilized that represent a range of motions. Analysis of measured prostate motions for fifteen patients was performed to ensure detected motions were similar to those previously reported and motion files utilized were suitable. Five patient plans were utilized to allow for the effects of MLC and target motion interplay to be investigated. For both motion compensation and gating techniques, plans were delivered to the stationary phantom and for each of four motion types with/without compensation/gating enabled. Using a 3%, 2mm and 80% threshold gamma criteria, film measurements had an average pass rate of 80.5% for uncorrected deliveries versus 96.0% for motion compensated deliveries. For gated techniques average pass rates increased from 89.9% for uncorrected to 94.8% with gating enabled. Measurements with the Delta4 arrays were analyzed with a 3%, 2mm and 10% threshold dose. An average pass rate of 83.8% was measured for uncorrected motions versus 94.8% with motion compensation. For the gated technique an average pass rate of 87.2% was found for uncorrected motions versus 96.9% with gating enabled. These results show that very high gamma pass rates are achievable when motion compensation or gating techniques are applied. When target motion is not accounted for shifts up to 5mm in planned versus delivered isodose distributions were found. However, when motion compensation, or gated techniques were applied, much smaller differences between planned and delivered isodose distributions were found. With these techniques dose delivery accuracy is greatly improved, allowing for PTV margins to be reduced.

Fetal Cardiovascular MRI - A Systemic Review of the Literature: Challenges, New Technical Developments, and Perspectives.

Fetal magnetic resonance imaging (MRI) has become a valuable adjunct to ultrasound in the prenatal diagnosis of congenital pathologies of the central nervous system, thorax, and abdomen. Fetal cardiovascular magnetic resonance (CMR) was limited, mainly by the lack of cardiac gating, and has only recently evolved due to technical developments. A literature search was performed on PubMed, focusing on technical advancements to perform fetal CMR. In total, 20 publications on cardiac gating techniques in the human fetus were analyzed. Fetal MRI is a safe imaging method with no developmental impairments found to be associated with in utero exposure to MRI. Fetal CMR is challenging due to general drawbacks (e. g., fetal motion) and specific limitations such as the difficulty to generate a cardiac gating signal to achieve high spatiotemporal resolution. Promising technical advancements include new methods for fetal cardiac gating, based on novel post-processing approaches and an external hardware device, as well as motion compensation and acceleration techniques. Newly developed direct and indirect gating approaches were successfully applied to achieve high-quality morphologic and functional imaging as well as quantitative assessment of fetal hemodynamics in research settings. In cases when prenatal echocardiography is limited, e. g., by an unfavorable fetal position in utero, or when its results are inconclusive, fetal CMR could potentially serve as a valuable adjunct in the prenatal assessment of congenital cardiovascular malformations. However, sufficient data on the diagnostic performance and clinical benefit of new fetal CMR techniques is still lacking. · New fetal cardiac gating methods allow high-quality fetal CMR.. · Motion compensation and acceleration techniques allow for improvement of image quality.. · Fetal CMR could potentially serve as an adjunct to fetal echocardiography in the future.. · Knapp J, Tavares de Sousa M, Schönnagel BP. Fetal Cardiovascular MRI - A Systemic Review of the Literature: Challenges, New Technical Developments, and Perspectives. Fortschr Röntgenstr 2022; 194: 841 - 851.

Technical note: Low-cost MR-compatible pneumatic respiratory organ motion simulator for the development of MR-guided thermal therapy.

In magnetic resonance (MR)-guided thermal therapy, respiratory motion can cause a significant temperature error in MR thermometry and reduce the efficiency of the treatment. A respiratory motion simulator is necessary for the development of new MR imaging (MRI) and motion compensation techniques. The purpose of this study is to develop a low-cost and simple MR-compatible respiratory motion simulator to support proof-of-concept studies of MR monitoring approaches with respiratory-induced abdominal organ motion. The phantom motion system integrates pneumatic control via an actuator subsystem located outside the MRI and coupled via plastic tubing to a compressible bag for distention and retraction within the MRI safe motion subsystem and phantom positioned within the MRI scanner. Performance of the respiratory motion simulator was evaluated with a real-time gradient echo MRI pulse sequence. The motion simulator can produce respiratory rates in the range of 8-16 breaths/min. Our experiments showed the consistent periodic motion of the phantom during MRI acquisition in the range of 3.7-9mm with 16 breaths/min. The operation of the simulator did not cause interference with MRI acquisition. In this study, we have demonstrated the ability of the motion simulator to generate controlled respiratory motion of a phantom. The low-cost MR-compatible respiratory motion simulator can be easily constructed from off-the-shelf and 3D-printed parts based on open-source 3D models and instructions. This could lower the barriers to the development of new MRI techniques with motion compensation.

Towards free breathing 3D ASL imaging of the human liver using prospective motion correction.

Measurements of liver perfusion yield valuable information about certain diseases like carcinomas and cirrhosis. To assess perfusion, noninvasive arterial spin labeling (ASL) MRI has the potential to become an important alternative to contrast agent-based methods. Unfortunately, ASL perfusion-weighted images are highly susceptible to breathing motion. This work presents a prospective motion-compensation technique, tackling breathing motion during ASL experiments of the human liver. Feasibility of 3D pseudo-continuous ASL imaging under free breathing is investigated by using a prospective motion-compensation technique with fat signal in additional 2D-EPI navigators. The proposed technique is compatible with strong signal suppression, occurring in background-suppressed pseudo-continuous ASL imaging. An additional retrospective 2D elastic registration algorithm is proposed to correct for residual elastic deformations. The technique is validated in 8 healthy volunteers. The prospective technique allowed a significant reduction of the cranial-caudal liver shifts during free breathing pseudo-continuous ASL experiments. Additional 2D elastic image registration allowed reduction of cranial-caudal liver motion to levels of timed breathing protocols. Artifacts in perfusion-weighted images could be reduced when compared with free-breathing ASL images without motion correction. The proposed technique is suitable for prospective compensation of liver motion in background-suppressed 3D pseudo-continuous ASL imaging. Future work focuses on further improving the quality of perfusion-weighted images.

Influence and compensation of patient motion in electromagnetic tracking based quality assurance in interstitial brachytherapy of the breast.

Electromagnetic tracking (EMT) is a versatile and viable technique for various quality assurance (QA) tasks in interstitial brachytherapy (iBT). As the duration of EMT measurements in iBT is on the order of minutes, they can be strongly affected by patient motion, especially breathing, which gives rise to motion artefacts. Since the centrepiece of EMT-related QA in iBT is to assess the geometry of the iBT implant or applicator, the absence of adequate motion compensation techniques could impede the use of EMT for QA purposes. A common way to compensate for this is to reference the data to either external or internal reference sensors (ERS, IRS) which are fixated on the patient's body or inside the applicator and therefore move with the patient. The purpose of the presented study is to provide a quantitative and in-depth analysis on the use of reference sensors for motion compensation. First, the need for adequate motion compensation is identified both qualitatively and quantitatively using a phantom subjected to simulated breathing motion. An evaluation routine is developed to assess the influence of motion compensation using reference sensors on the acquired EMT data. The evaluation metric is based on the observed displacement of the EMT sensor from its mean position while dwelling at a dwell position (DP) for a dwell time of 1 s. After that, the routine is applied to a cohort of 54 breast cancer patients treated with iBT, and the quality of an ERS based compensation approach is assessed. In a subgroup of four patients, an IRS is inserted into the iBT implant and IRS-based compensation is compared to the ERS-based approach. Moreover, a correlation analysis of the ERS and IRS approach is performed, also including respiratory signals derived from the trajectories of the different reference sensors. It was found that motion compensation with ERS effectively reduced the mean sensor displacement per DP to median values as low as 0.11 mm in both phantom and patient measurements, which is below the precision of the EMT system (0.48 mm). Compensation using the IRS yielded comparable results and was as good as compensation with ERS. The results obtained from both approaches showed a strong correlation. Also the respiratory signals calculated from the different reference sensors were well correlated in most cases. These results indicate that motion compensation with ERS can effectively remove motion artefacts in EMT data. While compensation with an IRS leads to comparable results, the IRS occupies one catheter whose geometry hence cannot be assessed. The use of ERS has proven to be both effective and practical in clinical routine.

Coarse-to-fine SVD-GAN based framework for enhanced frame synthesis

Frame interpolation and synthesis are growing topics in the field of computer vision. Hence, these topics gained more attention recently where several deep-learning architectures were proposed to enhance the quality of the synthesized frames. In this paper, an efficient handcrafted deep approach is proposed for better frame synthesis. The proposed approach takes advantage of singular value decomposition (SVD) framework and Generative Adversarial Networks (GAN). The proposed approach does not require any computationally expensive feature extraction steps such optical flow techniques and block-based motion compensation techniques. Nonetheless, the SVD components still carry the relevant motion information needed to deal with the challenges such as large motion and occlusion. Thus, the frames are temporally upscaled via SVD based construction procedure where new middle frames are interpolated for further enhancement using a GAN based approach that eliminates most of the visual artifacts. The proposed frame synthesis approach is comprehensively evaluated in different scenarios where its performance is assessed and compared with the state-of-the-art. Our framework outperforms the majority of the deep learning approaches in terms quantitative results in addition to qualitative results where our framework can generate smoother frames with less visual artifacts.

Optical-flow-based motion compensation algorithm in thermoelastic stress analysis using single-infrared video

&lt;p&gt;Thermoelastic stress analysis (TSA) is a non-contact measurement technique for stress distribution evaluation. A common issue related to this technique is the rigid-displacement of the specimen during the test phase, that can compromise the reliability of the measurement. For this purpose, several motion compensation techniques have been implemented over the years, but none of them is provided through a single measurement and a single sample surface conditioning. Due to this, a motion compensation technique based on Optical-Flow has been implemented, which greatly increases the strength and the effectiveness of the methodology through a single measurement and single specimen preparation. The proposed approach is based on measuring the displacement field of the specimen directly from the thermal video, through optical flow. This displacement field is then used to compensate for the specimen’s displacement on the infrared video, which will then be used for thermoelastic stress analysis. Firstly, the algorithm was validated by a comparison with synthetic videos, created ad hoc, and the quality of the motion compensation approach was evaluated on video acquired in the visible range. The research moved into infrared acquisitions, where the application of TSA gave reliable and accurate results. Finally, the quality of the stress map obtained was verified by comparison with a numerical model.&lt;/p&gt;